
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import calplot


df = pd.read_csv("data.csv")


focuscrimes = set(['WEAPON LAWS', 'PROSTITUTION', 'DRIVING UNDER THE INFLUENCE', 'ROBBERY', 'BURGLARY', 'ASSAULT', 'DRUNKENNESS', 'DRUG/NARCOTIC', 'TRESPASS', 'LARCENY/THEFT', 'VANDALISM', 'VEHICLE THEFT', 'STOLEN PROPERTY', 'DISORDERLY CONDUCT'])


f = df[df['Category'].isin(focuscrimes)]
f = f.copy()


f['Month'] = pd.to_datetime(f['Date']).dt.month
f['Hour'] = pd.to_datetime(f['Time'], format = '%H:%M').dt.hour


plt.figure(figsize = (15,25))
weekdays_order = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']

for i, crime in enumerate(focuscrimes, start =1):
    ax = plt.subplot(7, 2, i)
    f_temp =f[f['Category'] == crime]

    counts = f_temp['DayOfWeek'].value_counts().reindex(weekdays_order)
    
    for j, day in enumerate(weekdays_order):
        ax.bar(j, counts.loc[day], color='lavender', edgecolor = 'indigo', linewidth = 2, width=0.6)

    x = np.arange(len(weekdays_order))
    ax.set_xticks(x)
    ax.set_xticklabels(weekdays_order, rotation=90)
    ax.set_ylabel('Crime count')
    
    y_max = f_temp['DayOfWeek'].value_counts().max()
    ax.set_ylim(top=y_max * 1.3)  
    
    ax.text(0.02, 0.95, f'{crime}', transform=ax.transAxes, 
            horizontalalignment='left', verticalalignment='top', 
            fontsize=14 )

    if i > 12:
        ax.set_xlabel('Day of the Week')
        ax.set_xticklabels(ax.get_xticklabels(), rotation=90)
    else:
        ax.set_xlabel('')
        ax.set_xticklabels([])

    plt.tight_layout(pad=3.0)

plt.show()

/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/2757337662.py:32: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=3.0)


plt.figure(figsize = (16,28))
months_order = list(range(1,13))
months_labels = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']

for i, crime in enumerate(focuscrimes, start =1):
    ax = plt.subplot(7, 2, i)
    f_temp =f[f['Category'] == crime]

    counts = f_temp['Month'].value_counts().reindex(months_order)
    
    for j, month in enumerate(months_order):
        ax.bar(j, counts.loc[month], color='lavender', edgecolor = 'indigo', linewidth = 1, width=0.5)

    x = np.arange(len(months_order))
    ax.set_xticks(x)
    ax.set_xticklabels(months_labels, rotation=0)
    ax.set_ylabel('Crime count')
    
    y_max = counts.max()
    ax.set_ylim(top=y_max * 1.3)
    
    ax.text(0.02, 0.95, f'{crime}', transform=ax.transAxes, 
            horizontalalignment='left', verticalalignment='top', 
            fontsize=12 )

    if i > 12:
        ax.set_xlabel('Month of the Year')
        ax.set_xticklabels(ax.get_xticklabels(), rotation=0)
    else:
        ax.set_xlabel('')
        ax.set_xticklabels([])

    plt.tight_layout(pad=4.0) 
plt.show()

/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1260041138.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)


plt.figure(figsize = (16,28))
hours_order = list(range(0,24))
hours_labels = list(range(1,25))

for i, crime in enumerate(focuscrimes, start =1):
    ax = plt.subplot(7, 2, i)
    f_temp =f[f['Category'] == crime]

    counts = f_temp['Hour'].value_counts().reindex(hours_order)
    
    for j, hour in enumerate(hours_order):
        ax.bar(j, counts.loc[hour], color='lavender', edgecolor = 'indigo', linewidth = 1, width=0.5)

    x = np.arange(len(hours_order))
    ax.set_xticks(x)
    ax.set_xticklabels(hours_labels, rotation=0)
    ax.set_ylabel('Crime count')
    
    y_max = counts.max()
    ax.set_ylim(top=y_max * 1.3)
    
    ax.text(0.02, 0.95, f'{crime}', transform=ax.transAxes, 
            horizontalalignment='left', verticalalignment='top', 
            fontsize=12 )

    if i > 12:
        ax.set_xlabel('Hour of the day')
        ax.set_xticklabels(ax.get_xticklabels(), rotation=0)
    else:
        ax.set_xlabel('')
        ax.set_xticklabels([])

    plt.tight_layout(pad=4.0) 
plt.show()

/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1244553225.py:33: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)


day_to_num = {'Monday':0, 'Tuesday':1, 'Wednesday':2, 'Thursday':3, 'Friday': 4, 'Saturday':5, 'Sunday':6}
f['WeekHour'] = f['DayOfWeek'].map(day_to_num) * 24 + f['Hour']


plt.figure(figsize = (16,28))
week_hours_order = list(range(0,168))
weekdays_order = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']

for i, crime in enumerate(focuscrimes, start =1):
    ax = plt.subplot(7, 2, i)
    f_temp =f[f['Category'] == crime]
    
    counts = f_temp['WeekHour'].value_counts().reindex(week_hours_order)
    
    for j, hour in enumerate(week_hours_order):
        ax.bar(j, counts[hour], color='mediumpurple', edgecolor = 'indigo', linewidth = 0.08, width=0.5)

    x = list(range(0,168,24))
    ax.set_xticks(x)
    ax.set_xticklabels(weekdays_order, rotation=0)
    ax.set_ylabel('Crime count')
    
    y_max = counts.max()
    ax.set_ylim(top=y_max * 1.3)
    
    ax.text(0.02, 0.95, f'{crime}', transform=ax.transAxes, 
            horizontalalignment='left', verticalalignment='top', 
            fontsize=12 )
    
    for day in range(1, 7):
        plt.axvline(day * 24, color='silver', linestyle=':')
    
    if i > 12:
        ax.set_xlabel('Hour of the Week')
        ax.set_xticklabels(ax.get_xticklabels(), rotation=0)
    else:
        ax.set_xlabel('')
        ax.set_xticklabels([])

    plt.tight_layout(pad=4.0)
plt.savefig('168HourlyPatterns.png', dpi=300)
plt.show()

/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/391088015.py:36: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)


p = f[f['Category'] == 'PROSTITUTION']
p = p.copy()


p['Date'] = pd.to_datetime(p['Date'])


p_counts = p.groupby(pd.Grouper(key='Date', freq ='D')).size()


title = 'Calendar plot of the frequency of Prostitution Incidents from 2003-2018'
calplot.calplot(p_counts, suptitle = title, cmap = 'YlGn', tight_layout = True)
plt.tight_layout(pad=4.0)
plt.savefig('CalPlot YlGn.png', dpi = 300)

/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/523338368.py:3: UserWarning: This figure includes Axes that are not compatible with tight_layout, so results might be incorrect.
  plt.tight_layout(pad=4.0)
/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/523338368.py:3: UserWarning: The figure layout has changed to tight
  plt.tight_layout(pad=4.0)


dui = f[f['Category']== 'DRIVING UNDER THE INFLUENCE']
dui = dui.copy()


dui_counts = dui.groupby('Hour').size()


theta = np.linspace(0, 2*np.pi, 24, endpoint = False)


radii = dui_counts.values


fig, ax = plt.subplots(figsize=(8,8), subplot_kw={'projection':'polar'})

bars = ax.bar(theta, radii, width=2*np.pi/24.5, color='aliceblue', edgecolor = 'steelblue', align='edge')

ax.set_theta_offset(np.pi / 2)
ax.set_theta_direction(-1)

ax.set_xticks(theta)
ax.set_xticklabels([f'{i}:00' for i in range(24)])

plt.title('24-Hour Pattern of Driving Under the Influence Incidents')
plt.savefig('PolarPlot.png', dpi = 300)
plt.show()


data = df
focuscrimes = set(['WEAPON LAWS', 'PROSTITUTION', 'DRIVING UNDER THE INFLUENCE', 'ROBBERY', 'BURGLARY', 'ASSAULT', 'DRUNKENNESS', 'DRUG/NARCOTIC', 'TRESPASS', 'LARCENY/THEFT', 'VANDALISM', 'VEHICLE THEFT', 'STOLEN PROPERTY', 'DISORDERLY CONDUCT'])
data = data[data["Category"].isin(focuscrimes)]

crimes_per_day = data.groupby(['Category', 'Date']).size().reset_index(name = 'Incidents')
#print(crimes_per_day)

crimes_per_day.boxplot(by='Category', column='Incidents', figsize=(15,15))
plt.ylabel("Incidents")
plt.xticks(rotation=90)
plt.tight_layout()
plt.show()


districts = data["PdDistrict"].dropna().unique()

nrows = 5
ncols = 2
fig, axes = plt.subplots(nrows, ncols, figsize=(20, 20), sharey=True, sharex=True)
axes = axes.flatten()

for i,district in enumerate(districts):
    crime_data = data[data["PdDistrict"] == district]
    crime_district_counts = crime_data["Category"].value_counts(normalize=True).sort_index()
    
    axes[i].bar(crime_district_counts.index,crime_district_counts.values)
    axes[i].set_title(district)
    axes[i].set_xlabel("Category")
    axes[i].set_ylabel("Counts")
    axes[i].tick_params('x',labelrotation=90)

plt.tight_layout()
plt.show()


data["Date"] = pd.to_datetime(data["Date"], yearfirst=True)
data.set_index("Date", inplace=True)


category_data = data[data["Category"] == "LARCENY/THEFT"]

category_counts = category_data.resample("D").size()

calplot.calplot(category_counts, cmap='YlGn', yearlabel_kws={'fontname':'sans-serif'})
plt.show()

/var/folders/fk/jf1n3p615pj42c3yn8qkk3b80000gn/T/ipykernel_69114/1857008572.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  data["Date"] = pd.to_datetime(data["Date"], yearfirst=True)

Part	Contributor	Student ID
Part 1, Part 2	Dimasha Nanayakkara	s194710
Part 3	Ning Sun	s232171
Part 4	Max Heiberg Bestle	s194574

Assignment 1¶

A1 Part 1: Visualizing patterns in the data¶

A1 Part 2: Dataviz questions¶

A1 Part 3: Visualizing geodata using Plotly¶

Assignment 1 Part 4¶

1. Prostitution on Thursdays¶

Rounded up or down times of crimes¶

Sex offence hot spot at Hall of Justice¶

Human Noise in Dataset¶

LLMs¶

Contributions¶